Building a Multi-Channel Agent with Context Memory and Conversation Records

I want to build an agent where the user can choose to Whatsapp or Voice. I know I can build 2 separate ones. I'm wondering if there's a way for the agent to have multiple inputs (email, whatsapp, voice) and keep memory of the context of the person they're speaking to? So if the person comes back in via any of the channels, it will remember? Thirdly, is there a way for me to get a record of each conversation that's being had?